Loading...
Loading...
Found 6,253 Skills
This skill should be used when the user asks to refactor specific files or directories, simplify recently changed code, clean up dead code in a limited scope, or invokes `/refactor` with paths or semantic queries.
Based on the Recursive Language Models (RLM) research by Zhang, Kraska, and Khattab (2025), this skill provides strategies for handling tasks that exceed comfortable context limits through programmatic decomposition and recursive self-invocation. Triggers on phrases like "analyze all files", "process this large document", "aggregate information from", "search across the codebase", or tasks involving 10+ files or 50k+ tokens.
Agent skill for performance-optimizer - invoke with $agent-performance-optimizer
Use this skill to create investor pitch decks, partnership presentations, or business proposals. Triggers: "pitch deck", "investor deck", "fundraising presentation", "startup pitch", "investor presentation", "VC pitch", "seed deck", "series A deck", "business proposal", "partnership pitch", "sales deck", "demo day" Outputs: Structured slide content, talking points, and optional generated visuals.
Before starting any significant task, force explicit evaluation of available skills. For each potentially relevant skill, state YES/NO with reasoning. Only proceed to implementation after skills have been consciously evaluated and activated. Prevents the ~50% "coin flip" activation rate that occurs when skills are passively available but not deliberately considered.
Official Puppeteer Model Context Protocol Server for browser automation.
Automate browser tasks like form filling, data extraction, or multi-step web workflows. Use when the user needs to interact with websites that require clicking, typing, or navigation.
Conduct context-driven code reviews focusing on quality, testability, and maintainability. Use when reviewing code, providing feedback, or establishing review practices.
Synthesizes research findings into design decisions via codebase investigation. Use when (1) translating research into implementation approaches, (2) selecting between design alternatives, (3) executing after /research or deep-research, or (4) preparing input for /plan phase.
Activate when the user clearly has a skill issue. Generates chaotic, barely-functional code with maximum confidence and sarcastic commentary. Guarantees an infinite loop of attempted fixes that never quite land.
General Architecture Specification for CS-RAG Project, unifies global architecture cognition and architecture design constraints, provides entry points for layered inspection, impact analysis, interface contracts, dependency injection and pluggable governance.
Transform messy work updates into clean, standardized end-of-day Slack sync summaries. Use when asked to "format my updates", "create a sync", "write a standup", or "summarize my work" for Slack.